Back to skill

Security audit

Product Prompt Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides instructions for generating concise product image prompts and does not request sensitive access, persistence, or code execution.

Installers should expect this skill to generate short product-image prompts from product details and possibly analyze user-provided images or search for category knowledge. There is no evidence of hidden execution, data exfiltration, persistence, or credential access.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description explicitly says to generate 'English image prompts,' which imposes a language constraint. Under the policy criteria, forcing a specific language without offering the user a choice or opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The output section instructs the skill to emit the prompt directly as an '[English prompt]', reinforcing a mandatory language policy. No user choice, opt-in, or justified locale restriction is provided in the file.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.